Re: spamassassin ?
On 09 Mar 2004, Andrew Schulman wrote:
> > Perhaps this is drawing a red herring across the trail, but I can't help
> > wondering why more people don't use spamprobe in preference to
> > spamassassin. IME spamprobe is easier to set up and extremely effective.
> > I see only about 2 or 3 false negatives a day at most and no false
> > positives at all.
>
> I don't know anything about spamprobe. I think one reason people like
> spamassassin is that it has a mix of heuristic and learning (Bayesian)
> rules. And you can add your own rules to the list, based on regular
> expressions.
>
> As for the original question, I think the OP would have the same problem
> with spamprobe as with spamassassin-- it's really an exim problem.
Spamprobe is a Bayesian filter too. From the man page:
SpamProbe operates on a different basis entirely. Instead of
using pattern matching and a set of human generated rules
SpamProbe relies on a Bayesian analysis of the frequency of words
used in spam and non-spam emails received by an individual
person. The process is completely automatic and tailors itself
to the kinds of emails that each person receives.
AC
--
ac@acampbell.org.uk || http://www.acampbell.org.uk
using Linux GNU/Debian || for book reviews, electronic
Windows-free zone || books and skeptical articles
Reply to: